summaryrefslogtreecommitdiff
path: root/kernel/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/arraymap.c20
-rw-r--r--kernel/bpf/core.c53
-rw-r--r--kernel/bpf/hashtab.c24
-rw-r--r--kernel/bpf/stackmap.c20
-rw-r--r--kernel/bpf/syscall.c72
-rw-r--r--kernel/bpf/verifier.c28
6 files changed, 140 insertions, 77 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index a2ac051c342f..3d55d95dcf49 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -11,7 +11,6 @@
*/
#include <linux/bpf.h>
#include <linux/err.h>
-#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/filter.h>
@@ -56,7 +55,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
attr->value_size == 0 || attr->map_flags)
return ERR_PTR(-EINVAL);
- if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1))
+ if (attr->value_size > KMALLOC_MAX_SIZE)
/* if value_size is bigger, the user space won't be able to
* access the elements.
*/
@@ -74,14 +73,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
if (array_size >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-ENOMEM);
-
/* allocate all map elements and zero-initialize them */
- array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
- if (!array) {
- array = vzalloc(array_size);
- if (!array)
- return ERR_PTR(-ENOMEM);
- }
+ array = bpf_map_area_alloc(array_size);
+ if (!array)
+ return ERR_PTR(-ENOMEM);
/* copy mandatory map attributes */
array->map.map_type = attr->map_type;
@@ -97,7 +92,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
if (array_size >= U32_MAX - PAGE_SIZE ||
elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
- kvfree(array);
+ bpf_map_area_free(array);
return ERR_PTR(-ENOMEM);
}
out:
@@ -262,7 +257,7 @@ static void array_map_free(struct bpf_map *map)
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
bpf_array_free_percpu(array);
- kvfree(array);
+ bpf_map_area_free(array);
}
static const struct bpf_map_ops array_ops = {
@@ -319,7 +314,8 @@ static void fd_array_map_free(struct bpf_map *map)
/* make sure it's empty */
for (i = 0; i < array->map.max_entries; i++)
BUG_ON(array->ptrs[i] != NULL);
- kvfree(array);
+
+ bpf_map_area_free(array);
}
static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 83e0d153b0b4..503d4211988a 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -105,19 +105,29 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO |
gfp_extra_flags;
struct bpf_prog *fp;
+ u32 pages, delta;
+ int ret;
BUG_ON(fp_old == NULL);
size = round_up(size, PAGE_SIZE);
- if (size <= fp_old->pages * PAGE_SIZE)
+ pages = size / PAGE_SIZE;
+ if (pages <= fp_old->pages)
return fp_old;
+ delta = pages - fp_old->pages;
+ ret = __bpf_prog_charge(fp_old->aux->user, delta);
+ if (ret)
+ return NULL;
+
fp = __vmalloc(size, gfp_flags, PAGE_KERNEL);
- if (fp != NULL) {
+ if (fp == NULL) {
+ __bpf_prog_uncharge(fp_old->aux->user, delta);
+ } else {
kmemcheck_annotate_bitfield(fp, meta);
memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE);
- fp->pages = size / PAGE_SIZE;
+ fp->pages = pages;
fp->aux->prog = fp;
/* We keep fp->aux from fp_old around in the new
@@ -136,28 +146,30 @@ void __bpf_prog_free(struct bpf_prog *fp)
vfree(fp);
}
-#define SHA_BPF_RAW_SIZE \
- round_up(MAX_BPF_SIZE + sizeof(__be64) + 1, SHA_MESSAGE_BYTES)
-
-/* Called under verifier mutex. */
-void bpf_prog_calc_digest(struct bpf_prog *fp)
+int bpf_prog_calc_tag(struct bpf_prog *fp)
{
const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64);
- static u32 ws[SHA_WORKSPACE_WORDS];
- static u8 raw[SHA_BPF_RAW_SIZE];
- struct bpf_insn *dst = (void *)raw;
+ u32 raw_size = bpf_prog_tag_scratch_size(fp);
+ u32 digest[SHA_DIGEST_WORDS];
+ u32 ws[SHA_WORKSPACE_WORDS];
u32 i, bsize, psize, blocks;
+ struct bpf_insn *dst;
bool was_ld_map;
- u8 *todo = raw;
+ u8 *raw, *todo;
__be32 *result;
__be64 *bits;
- sha_init(fp->digest);
+ raw = vmalloc(raw_size);
+ if (!raw)
+ return -ENOMEM;
+
+ sha_init(digest);
memset(ws, 0, sizeof(ws));
/* We need to take out the map fd for the digest calculation
* since they are unstable from user space side.
*/
+ dst = (void *)raw;
for (i = 0, was_ld_map = false; i < fp->len; i++) {
dst[i] = fp->insnsi[i];
if (!was_ld_map &&
@@ -177,12 +189,13 @@ void bpf_prog_calc_digest(struct bpf_prog *fp)
}
}
- psize = fp->len * sizeof(struct bpf_insn);
- memset(&raw[psize], 0, sizeof(raw) - psize);
+ psize = bpf_prog_insn_size(fp);
+ memset(&raw[psize], 0, raw_size - psize);
raw[psize++] = 0x80;
bsize = round_up(psize, SHA_MESSAGE_BYTES);
blocks = bsize / SHA_MESSAGE_BYTES;
+ todo = raw;
if (bsize - psize >= sizeof(__be64)) {
bits = (__be64 *)(todo + bsize - sizeof(__be64));
} else {
@@ -192,13 +205,17 @@ void bpf_prog_calc_digest(struct bpf_prog *fp)
*bits = cpu_to_be64((psize - 1) << 3);
while (blocks--) {
- sha_transform(fp->digest, todo, ws);
+ sha_transform(digest, todo, ws);
todo += SHA_MESSAGE_BYTES;
}
- result = (__force __be32 *)fp->digest;
+ result = (__force __be32 *)digest;
for (i = 0; i < SHA_DIGEST_WORDS; i++)
- result[i] = cpu_to_be32(fp->digest[i]);
+ result[i] = cpu_to_be32(digest[i]);
+ memcpy(fp->tag, result, sizeof(fp->tag));
+
+ vfree(raw);
+ return 0;
}
static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 34debc1a9641..a753bbe7df0a 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -13,7 +13,6 @@
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
-#include <linux/vmalloc.h>
#include "percpu_freelist.h"
#include "bpf_lru_list.h"
@@ -103,7 +102,7 @@ static void htab_free_elems(struct bpf_htab *htab)
free_percpu(pptr);
}
free_elems:
- vfree(htab->elems);
+ bpf_map_area_free(htab->elems);
}
static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
@@ -125,7 +124,8 @@ static int prealloc_init(struct bpf_htab *htab)
{
int err = -ENOMEM, i;
- htab->elems = vzalloc(htab->elem_size * htab->map.max_entries);
+ htab->elems = bpf_map_area_alloc(htab->elem_size *
+ htab->map.max_entries);
if (!htab->elems)
return -ENOMEM;
@@ -274,7 +274,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
*/
goto free_htab;
- if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) -
+ if (htab->map.value_size >= KMALLOC_MAX_SIZE -
MAX_BPF_STACK - sizeof(struct htab_elem))
/* if value_size is bigger, the user space won't be able to
* access the elements via bpf syscall. This check also makes
@@ -320,14 +320,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
goto free_htab;
err = -ENOMEM;
- htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket),
- GFP_USER | __GFP_NOWARN);
-
- if (!htab->buckets) {
- htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket));
- if (!htab->buckets)
- goto free_htab;
- }
+ htab->buckets = bpf_map_area_alloc(htab->n_buckets *
+ sizeof(struct bucket));
+ if (!htab->buckets)
+ goto free_htab;
for (i = 0; i < htab->n_buckets; i++) {
INIT_HLIST_HEAD(&htab->buckets[i].head);
@@ -354,7 +350,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
free_extra_elems:
free_percpu(htab->extra_elems);
free_buckets:
- kvfree(htab->buckets);
+ bpf_map_area_free(htab->buckets);
free_htab:
kfree(htab);
return ERR_PTR(err);
@@ -1014,7 +1010,7 @@ static void htab_map_free(struct bpf_map *map)
prealloc_destroy(htab);
free_percpu(htab->extra_elems);
- kvfree(htab->buckets);
+ bpf_map_area_free(htab->buckets);
kfree(htab);
}
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 732ae16d12b7..be8519148c25 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -7,7 +7,6 @@
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
-#include <linux/vmalloc.h>
#include <linux/stacktrace.h>
#include <linux/perf_event.h>
#include "percpu_freelist.h"
@@ -32,7 +31,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
int err;
- smap->elems = vzalloc(elem_size * smap->map.max_entries);
+ smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries);
if (!smap->elems)
return -ENOMEM;
@@ -45,7 +44,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
return 0;
free_elems:
- vfree(smap->elems);
+ bpf_map_area_free(smap->elems);
return err;
}
@@ -76,12 +75,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-E2BIG);
- smap = kzalloc(cost, GFP_USER | __GFP_NOWARN);
- if (!smap) {
- smap = vzalloc(cost);
- if (!smap)
- return ERR_PTR(-ENOMEM);
- }
+ smap = bpf_map_area_alloc(cost);
+ if (!smap)
+ return ERR_PTR(-ENOMEM);
err = -E2BIG;
cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
@@ -112,7 +108,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
put_buffers:
put_callchain_buffers();
free_smap:
- kvfree(smap);
+ bpf_map_area_free(smap);
return ERR_PTR(err);
}
@@ -262,9 +258,9 @@ static void stack_map_free(struct bpf_map *map)
/* wait for bpf programs to complete before freeing stack map */
synchronize_rcu();
- vfree(smap->elems);
+ bpf_map_area_free(smap->elems);
pcpu_freelist_destroy(&smap->freelist);
- kvfree(smap);
+ bpf_map_area_free(smap);
put_callchain_buffers();
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4819ec9d95f6..19b6129eab23 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -12,6 +12,8 @@
#include <linux/bpf.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mmzone.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/license.h>
@@ -49,6 +51,30 @@ void bpf_register_map_type(struct bpf_map_type_list *tl)
list_add(&tl->list_node, &bpf_map_types);
}
+void *bpf_map_area_alloc(size_t size)
+{
+ /* We definitely need __GFP_NORETRY, so OOM killer doesn't
+ * trigger under memory pressure as we really just want to
+ * fail instead.
+ */
+ const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
+ void *area;
+
+ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+ area = kmalloc(size, GFP_USER | flags);
+ if (area != NULL)
+ return area;
+ }
+
+ return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags,
+ PAGE_KERNEL);
+}
+
+void bpf_map_area_free(void *area)
+{
+ kvfree(area);
+}
+
int bpf_map_precharge_memlock(u32 pages)
{
struct user_struct *user = get_current_user();
@@ -615,19 +641,39 @@ static void free_used_maps(struct bpf_prog_aux *aux)
kfree(aux->used_maps);
}
+int __bpf_prog_charge(struct user_struct *user, u32 pages)
+{
+ unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ unsigned long user_bufs;
+
+ if (user) {
+ user_bufs = atomic_long_add_return(pages, &user->locked_vm);
+ if (user_bufs > memlock_limit) {
+ atomic_long_sub(pages, &user->locked_vm);
+ return -EPERM;
+ }
+ }
+
+ return 0;
+}
+
+void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
+{
+ if (user)
+ atomic_long_sub(pages, &user->locked_vm);
+}
+
static int bpf_prog_charge_memlock(struct bpf_prog *prog)
{
struct user_struct *user = get_current_user();
- unsigned long memlock_limit;
-
- memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ int ret;
- atomic_long_add(prog->pages, &user->locked_vm);
- if (atomic_long_read(&user->locked_vm) > memlock_limit) {
- atomic_long_sub(prog->pages, &user->locked_vm);
+ ret = __bpf_prog_charge(user, prog->pages);
+ if (ret) {
free_uid(user);
- return -EPERM;
+ return ret;
}
+
prog->aux->user = user;
return 0;
}
@@ -636,7 +682,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
{
struct user_struct *user = prog->aux->user;
- atomic_long_sub(prog->pages, &user->locked_vm);
+ __bpf_prog_uncharge(user, prog->pages);
free_uid(user);
}
@@ -668,17 +714,17 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_prog *prog = filp->private_data;
- char prog_digest[sizeof(prog->digest) * 2 + 1] = { };
+ char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
- bin2hex(prog_digest, prog->digest, sizeof(prog->digest));
+ bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
seq_printf(m,
"prog_type:\t%u\n"
"prog_jited:\t%u\n"
- "prog_digest:\t%s\n"
+ "prog_tag:\t%s\n"
"memlock:\t%llu\n",
prog->type,
prog->jited,
- prog_digest,
+ prog_tag,
prog->pages * 1ULL << PAGE_SHIFT);
}
#endif
@@ -811,7 +857,7 @@ static int bpf_prog_load(union bpf_attr *attr)
err = -EFAULT;
if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
- prog->len * sizeof(struct bpf_insn)) != 0)
+ bpf_prog_insn_size(prog)) != 0)
goto free_prog;
prog->orig_prog = NULL;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d28f9a3380a9..cdc43b899f28 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -462,14 +462,19 @@ static void init_reg_state(struct bpf_reg_state *regs)
regs[BPF_REG_1].type = PTR_TO_CTX;
}
-static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
+static void __mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
{
- BUG_ON(regno >= MAX_BPF_REG);
regs[regno].type = UNKNOWN_VALUE;
regs[regno].id = 0;
regs[regno].imm = 0;
}
+static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno)
+{
+ BUG_ON(regno >= MAX_BPF_REG);
+ __mark_reg_unknown_value(regs, regno);
+}
+
static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
{
regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
@@ -1970,8 +1975,13 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
reg->type = type;
+ /* We don't need id from this point onwards anymore, thus we
+ * should better reset it, so that state pruning has chances
+ * to take effect.
+ */
+ reg->id = 0;
if (type == UNKNOWN_VALUE)
- mark_reg_unknown_value(regs, regno);
+ __mark_reg_unknown_value(regs, regno);
}
}
@@ -1982,16 +1992,16 @@ static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
enum bpf_reg_type type)
{
struct bpf_reg_state *regs = state->regs;
+ u32 id = regs[regno].id;
int i;
for (i = 0; i < MAX_BPF_REG; i++)
- mark_map_reg(regs, i, regs[regno].id, type);
+ mark_map_reg(regs, i, id, type);
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
if (state->stack_slot_type[i] != STACK_SPILL)
continue;
- mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE,
- regs[regno].id, type);
+ mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, type);
}
}
@@ -2926,6 +2936,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
int insn_cnt = env->prog->len;
int i, j, err;
+ err = bpf_prog_calc_tag(env->prog);
+ if (err)
+ return err;
+
for (i = 0; i < insn_cnt; i++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
(BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
@@ -3173,8 +3187,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
log_level = 0;
}
- bpf_prog_calc_digest(env->prog);
-
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
goto skip_full_check;
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-29 06:53:11 +0000